Online Self-Calibration Against Hallucination in Vision-Language Models
Open paper
Benchmark
Model
Rank
Results
object-hallucination-evaluation-on-pope
LLaVA-1.5-7B (OSCAR)
–
F1: 86.22
visual-question-answering-on-mm-vet
LLaVA-1.5-7B (OSCAR)
–
GPT-4 score: 34.6
Rank counts only results with a code link.